Lab Home | Phone | Search
Center for Nonlinear Studies  Center for Nonlinear Studies
 Home 
 People 
 Current 
 Affiliates 
 Visitors 
 Students 
 Research 
 ICAM-LANL 
 Publications 
 Conferences 
 Workshops 
 Sponsorship 
 Talks 
 Colloquia 
 Colloquia Archive 
 Seminars 
 Postdoc Seminars Archive 
 Quantum Lunch 
 Quantum Lunch Archive 
 CMS Colloquia 
 Q-Mat Seminars 
 Q-Mat Seminars Archive 
 P/T Colloquia 
 Archive 
 Kac Lectures 
 Kac Fellows 
 Dist. Quant. Lecture 
 Ulam Scholar 
 Colloquia 
 
 Jobs 
 Postdocs 
 CNLS Fellowship Application 
 Students 
 Student Program 
 Visitors 
 Description 
 Past Visitors 
 Services 
 General 
 
 History of CNLS 
 
 Maps, Directions 
 CNLS Office 
 T-Division 
 LANL 
 
Wednesday, June 01, 2016
3:00 PM - 4:00 PM
CNLS Conference Room (TA-3, Bldg 1690)

Seminar

Exploiting Low-dimensional Geometric Structure in High-dimensional Data: Lessons from Neuroscience for Machine Learning

Christopher Rozell
Georgia Institute of Technology

Modern data science has shown that low-dimensional models (e.g., sparsity, manifolds, attractors) are a powerful way to approximately capture the information in high-dimensional data. Our recent work lends evidence to the postulate that sensory neural systems may exploiting this type of structure for efficient information processing. Additionally, the explosion in neurotechnology research is presenting new challenges that require novel algorithmic approaches to manage the resulting data acquisition, storage and processing. In this talk I will review some of our recent work in modeling and data analysis techniques that exploit the low-dimensional structure in many types of data. While this work is motivated by our study of neural systems, I will show the applicability to machine learning tasks such as dimensionality reduction, manifold learning, transfer learning, and computer vision. Christopher J. Rozell received a B.S.E. degree in Computer Engineering and a B.F.A. degree in Music (Performing Arts Technology) in 2000 from the University of Michigan. He attended graduate school at Rice University, receiving the M.S. and Ph.D. degrees in Electrical Engineering in 2002 and 2007, respectively. Following graduate school he joined the Redwood Center for theoretical Neuroscience at the University of California, Berkeley as a postdoctoral scholar. In 2008, Dr. Rozell joined the faculty at the Georgia Institute of Technology where he is currently an Associate Professor in Electrical and Computer Engineering and he previously held the Demetrius T. Paris Junior Professorship. He has additional courtesy appointments in the Department of Biomedical Engineering and the School of Interactive Computing. His research interests live at the intersection of computational neuroscience, machine learning, signal processing, complex systems, and human-computer interaction. In 2014, Dr. Rozell was one of six international recipients of the Scholar Award in Studying Complex Systems from the James S. McDonnell Foundation 21st Century Science Initiative, as well as receiving a National Science Foundation CAREER Award and a Sigma Xi Young Faculty Research Award. In addition to his research activity, Dr. Rozell was awarded the CETL/BP Junior Faculty Teaching Excellence Award at Georgia Tech in 2013.

Host: Garrett Kenyon